While our understanding of fairness in machine learning has significantly progressed, our understanding of fairness in reinforcement learning (RL) remains nascent. Most of the attention has been on fairness in one-shot classification tasks; however, real-world, RL-enabled systems (e.g., autonomous vehicles) are much more complicated in that agents operate in dynamic environments over a long period of time. To ensure the responsible development and deployment of these systems, we must better understand fairness in RL. In this paper, we survey the literature to provide the most up-to-date snapshot of the frontiers of fairness in RL. We start by reviewing where fairness considerations can arise in RL, then discuss the various definitions of fairness in RL that have been put forth thus far. We continue to highlight the methodologies researchers used to implement fairness in single- and multi-agent RL systems before showcasing the distinct application domains that fair RL has been investigated in. Finally, we critically examine gaps in the literature, such as understanding fairness in the context of RLHF, that still need to be addressed in future work to truly operationalize fair RL in real-world systems.

We explore the use of deep reinforcement learning to audit an automatic short answer grading (ASAG) model. Automatic grading may decrease the time burden of rating open-ended items for educators, but a lack of robust evaluation methods for these models can result in uncertainty of their quality. Current state-of-the-art ASAG models are configured to match human ratings from a training set, and researchers typically assess their quality with accuracy metrics that signify agreement between model and human scores. In this paper, we show that a high level of agreement to human ratings does not give sufficient evidence that an ASAG model is infallible. We train a reinforcement learning agent to revise student responses with the objective of achieving a high rating from an automatic grading model in the least number of revisions. By analyzing the agent's revised responses that achieve a high grade from the ASAG model but would not be considered a high scoring responses according to a scoring rubric, we discover ways in which the automated grader can be exploited, exposing shortcomings in the grading model.

Generative AI (GenAI) has spurred the expectation of being creative, due to its ability to generate content, yet so far, its creativity has somewhat disappointed, because it is trained using existing data following human intentions to generate outputs. The purpose of this paper is to explore what is required to evolve AI from generative to creative. Based on a reinforcement learning approach and building upon various research streams of computational creativity, we develop a triple prompt-response-reward engineering framework to develop the creative capability of GenAI. This framework consists of three components: 1) a prompt model for expected creativity by developing discriminative prompts that are objectively, individually, or socially novel, 2) a response model for observed creativity by generating surprising outputs that are incrementally, disruptively, or radically innovative, and 3) a reward model for improving creativity over time by incorporating feedback from the AI, the creator/manager, and/or the customers. This framework enables the application of GenAI for various levels of creativity strategically.

Cooperative Multi-Agent Reinforcement Learning (MARL) necessitates seamless collaboration among agents, often represented by an underlying relation graph. Existing methods for learning this graph primarily focus on agent-pair relations, neglecting higher-order relationships. While several approaches attempt to extend cooperation modelling to encompass behaviour similarities within groups, they commonly fall short in concurrently learning the latent graph, thereby constraining the information exchange among partially observed agents. To overcome these limitations, we present a novel approach to infer the Group-Aware Coordination Graph (GACG), which is designed to capture both the cooperation between agent pairs based on current observations and group-level dependencies from behaviour patterns observed across trajectories. This graph is further used in graph convolution for information exchange between agents during decision-making. To further ensure behavioural consistency among agents within the same group, we introduce a group distance loss, which promotes group cohesion and encourages specialization between groups. Our evaluations, conducted on StarCraft II micromanagement tasks, demonstrate GACG's superior performance. An ablation study further provides experimental evidence of the effectiveness of each component of our method.

Developing new drugs is laborious and costly, demanding extensive time investment. In this study, we introduce an innovative de-novo drug design strategy, which harnesses the capabilities of language models to devise targeted drugs for specific proteins. Employing a Reinforcement Learning (RL) framework utilizing Proximal Policy Optimization (PPO), we refine the model to acquire a policy for generating drugs tailored to protein targets. Our method integrates a composite reward function, combining considerations of drug-target interaction and molecular validity. Following RL fine-tuning, our approach demonstrates promising outcomes, yielding notable improvements in molecular validity, interaction efficacy, and critical chemical properties, achieving 65.37 for Quantitative Estimation of Drug-likeness (QED), 321.55 for Molecular Weight (MW), and 4.47 for Octanol-Water Partition Coefficient (logP), respectively. Furthermore, out of the generated drugs, only 0.041\% do not exhibit novelty.

Federated Learning faces significant challenges in statistical and system heterogeneity, along with high energy consumption, necessitating efficient client selection strategies. Traditional approaches, including heuristic and learning-based methods, fall short of addressing these complexities holistically. In response, we propose FedGCS, a novel generative client selection framework that innovatively recasts the client selection process as a generative task. Drawing inspiration from the methodologies used in large language models, FedGCS efficiently encodes abundant decision-making knowledge within a continuous representation space, enabling efficient gradient-based optimization to search for optimal client selection that will be finally output via generation. The framework comprises four steps: (1) automatic collection of diverse "selection-score" pair data using classical client selection methods; (2) training an encoder-evaluator-decoder framework on this data to construct a continuous representation space; (3) employing gradient-based optimization in this space for optimal client selection; (4) generating the final optimal client selection via using beam search for the well-trained decoder. FedGCS outperforms traditional methods by being more comprehensive, generalizable, and efficient, simultaneously optimizing for model performance, latency, and energy consumption. The effectiveness of FedGCS is proven through extensive experimental analyses.

We consider the problem of learning an $\varepsilon$-optimal policy in a general class of continuous-space Markov decision processes (MDPs) having smooth Bellman operators. Given access to a generative model, we achieve rate-optimal sample complexity by performing a simple, \emph{perturbed} version of least-squares value iteration with orthogonal trigonometric polynomials as features. Key to our solution is a novel projection technique based on ideas from harmonic analysis. Our~$\widetilde{\mathcal{O}}(\epsilon^{-2-d/(\nu+1)})$ sample complexity, where $d$ is the dimension of the state-action space and $\nu$ the order of smoothness, recovers the state-of-the-art result of discretization approaches for the special case of Lipschitz MDPs $(\nu=0)$. At the same time, for $\nu\to\infty$, it recovers and greatly generalizes the $\mathcal{O}(\epsilon^{-2})$ rate of low-rank MDPs, which are more amenable to regression approaches. In this sense, our result bridges the gap between two popular but conflicting perspectives on continuous-space MDPs.

Across a wide range of hardware scenarios, the computational efficiency and physical size of the arithmetic units significantly influence the speed and footprint of the overall hardware system. Nevertheless, the effectiveness of prior arithmetic design techniques proves inadequate, as it does not sufficiently optimize speed and area, resulting in a reduced processing rate and larger module size. To boost the arithmetic performance, in this work, we focus on the two most common and fundamental arithmetic modules: adders and multipliers. We cast the design tasks as single-player tree generation games, leveraging reinforcement learning techniques to optimize their arithmetic tree structures. Such a tree generation formulation allows us to efficiently navigate the vast search space and discover superior arithmetic designs that improve computational efficiency and hardware size within just a few hours. For adders, our approach discovers designs of 128-bit adders that achieve Pareto optimality in theoretical metrics. Compared with the state-of-the-art PrefixRL, our method decreases computational delay and hardware size by up to 26% and 30%, respectively. For multipliers, when compared to RL-MUL, our approach increases speed and reduces size by as much as 49% and 45%. Moreover, the inherent flexibility and scalability of our method enable us to deploy our designs into cutting-edge technologies, as we show that they can be seamlessly integrated into 7nm technology. We believe our work will offer valuable insights into hardware design, further accelerating speed and reducing size through the refined search space and our tree generation methodologies. See our introduction video at https://bit.ly/ArithmeticTree. Codes are released at https://github.com/laiyao1/ArithmeticTree.

Robotics has been a popular field of research in the past few decades, with much success in industrial applications such as manufacturing and logistics. This success is led by clearly defined use cases and controlled operating environments. However, robotics has yet to make a large impact in domestic settings. This is due in part to the difficulty and complexity of designing mass-manufactured robots that can succeed in the variety of homes and environments that humans live in and that can operate safely in close proximity to humans. This paper explores the use of contextual affordances to enable safe exploration and learning in robotic scenarios targeted in the home. In particular, we propose a simple state representation that allows us to extend contextual affordances to larger state spaces and showcase how affordances can improve the success and convergence rate of a reinforcement learning algorithm in simulation. Our results suggest that after further iterations, it is possible to consider the implementation of this approach in a real robot manipulator. Furthermore, in the long term, this work could be the foundation for future explorations of human-robot interactions in complex domestic environments. This could be possible once state-of-the-art robot manipulators achieve the required level of dexterity for the described affordances in this paper.

This article leverages deep reinforcement learning (DRL) to hedge American put options, utilizing the deep deterministic policy gradient (DDPG) method. The agents are first trained and tested with Geometric Brownian Motion (GBM) asset paths and demonstrate superior performance over traditional strategies like the Black-Scholes (BS) Delta, particularly in the presence of transaction costs. To assess the real-world applicability of DRL hedging, a second round of experiments uses a market calibrated stochastic volatility model to train DRL agents. Specifically, 80 put options across 8 symbols are collected, stochastic volatility model coefficients are calibrated for each symbol, and a DRL agent is trained for each of the 80 options by simulating paths of the respective calibrated model. Not only do DRL agents outperform the BS Delta method when testing is conducted using the same calibrated stochastic volatility model data from training, but DRL agents achieves better results when hedging the true asset path that occurred between the option sale date and the maturity. As such, not only does this study present the first DRL agents tailored for American put option hedging, but results on both simulated and empirical market testing data also suggest the optimality of DRL agents over the BS Delta method in real-world scenarios. Finally, note that this study employs a model-agnostic Chebyshev interpolation method to provide DRL agents with option prices at each time step when a stochastic volatility model is used, thereby providing a general framework for an easy extension to more complex underlying asset processes.